Suitability of different machine learning methods for high-speed flow modeling issues
Open Access
- 31 December 2023
- journal article
- research article
- Published by Institute for Problems in Mechanical Engineering of the Russian Academy of Sciences - IPME RAS in Cybernetics and Physics
- No. Volume 12,
Abstract
In the present study, machine learning algorithms are applied for modeling transport coefficients in strongly nonequilibrium reacting gas flows. As a model case, the problem of a high-speed flow of a five-component air mixture around a sphere is considered. Various approaches for an application of machine learning methods, such as linear regression, k-nearest neighbors, support vector machine, regression tree, random forest, gradient boosting, and neural network (multilayer perceptron) are investigated. For the transport coefficients regression modelling the combination of machine learning methods with the finite volume method is constructed. The machine learning regressors are trained on the accurate numerical data given by one-temperature approach of the kinetic theory. The results of trained models are compared with approximate formulae of Blottner-Eucken-Wilke model. The results of different machine learning methods are analyzed in terms of the relationship between the obtained accuracy of calculations and the overall speed of calculations. The overall time of dataset formation and model training is estimated. The design of the constructed multilayer perceptron is discussed. The machine learning methods considered in the article can be used for the engineering problem such as design of high-speed aircraft, as well as for modeling of flows around complex shape bodies.Keywords
This publication has 27 references indexed in Scilit:
- PythonFOAM: In-situ data analyses with OpenFOAM and PythonJournal of Computational Science, 2022
- On developing data-driven turbulence model for DG solution of RANSChinese Journal of Aeronautics, 2019
- PAINeT: Similarity criteria and different approaches of kinetic theory2019
- PAINeT: An object-oriented software package for simulations of flow-field, transport coefficients and flux terms in non-equilibrium gas mixture flowsAIP Conference Proceedings, 2018
- Transport coefficients and heat fluxes in non-equilibrium high-temperature flows with electronic excitationPhysics of Plasmas, 2017
- Eucken correction in high-temperature gases with electronic excitationThe Journal of Chemical Physics, 2014
- Hypervelocity shock standoff on spheres in airShock Waves, 2013
- Nonequilibrium Hypersonic AerothermodynamicsPhysics Today, 1991
- Thermal Conductivity of Gas Mixtures in Chemical EquilibriumThe Journal of Chemical Physics, 1957
- A Viscosity Equation for Gas MixturesThe Journal of Chemical Physics, 1950